Upload NLPEvaluation_SIGMOID.py

NLPEvaluation_SIGMOID.py

@@ -0,0 +1,88 @@
+import gradio as gr
+import pandas as pd
+
+
+def auth(username, password):
+    if username == "SIGMOID" and password == "2A4S39H7E7GR1172":
+        return True
+    else:
+        return False
+
+
+def predict(df):
+    # LOAD TRAINER AND TOKENIZER AND TOKENIZE DATA
+    from transformers import AutoModel, AutoTokenizer, TrainingArguments, Trainer, BertForSequenceClassification
+    from datasets import Dataset
+    import numpy as np
+    model = BertForSequenceClassification.from_pretrained("sentiment_model", num_labels = 6)
+    tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-turkish-cased")
+
+    df_ids = df.pop('id')
+    test_dataset = Dataset.from_dict(df)
+    
+    from transformers import AutoTokenizer
+    
+    def tokenize_function(examples):
+        return tokenizer(examples["text"], padding="max_length", truncation=True)
+
+    tokenized_test_datasets = test_dataset.map(tokenize_function, batched=True)
+    
+    trainer = Trainer(
+            model=model,                         # the instantiated Transformers model to be trained
+    )
+    
+    # PREDICT TEXT VALUES USING LOADED MODEL AND EDIT DATAFRAME'S OFFANSIVE AND TARGET COLUMNS
+    preds = trainer.predict(tokenized_test_datasets)
+    max_indices = np.argmax(preds[0], axis=1)
+    
+    df['offansive'] = None
+    df['target'] = None
+    
+    for i in range(len(df)):
+        if max_indices[i] == 0:
+            df['offansive'][i] = 1
+            df["target"][i] = 'INSULT'
+
+        elif max_indices[i] == 1:
+            df['offansive'][i] = 1
+            df["target"][i] = 'RACIST'
+
+        elif max_indices[i] == 2:
+            df['offansive'][i] = 1
+            df["target"][i] = 'SEXIST'
+
+        elif max_indices[i] == 3:
+            df['offansive'][i] = 1
+            df["target"][i] = 'PROFANITY'
+
+        elif max_indices[i] == 4:
+            df['offansive'][i] = 0
+            df["target"][i] = 'OTHER'
+
+        elif max_indices[i] == 5:
+            df['offansive'][i] = 1
+            df["target"][i] = 'OTHER'
+    
+    df['id'] = df_ids
+    # *********** END ***********
+    return df
+
+def get_file(file):
+    output_file = "output_SIGMOID.csv"
+
+    # For windows users, replace path seperator
+    file_name = file.name.replace("\\", "/")
+
+    df = pd.read_csv(file_name, sep="|")
+
+    predict(df)
+    df.to_csv(output_file, index=False, sep="|")
+    return (output_file)
+
+
+
+# Launch the interface with user password
+iface = gr.Interface(get_file, "file", "file")
+
+if __name__ == "__main__":
+    iface.launch(share=True, auth=auth)